Replication Package: Early-Stage Prediction of Review Effort in AI-Generated Pull Requests (MSR 2026 Mining Challenge)
Replication Package: Early-Stage Prediction of Review Effort in AI-Generated Pull Requests (MSR 2026 Mining Challenge)
This repository contains the replication package for the MSR 2026 Mining Challenge paper “Early-Stage Prediction of Review Effort in AI-Generated Pull Requests”. It includes scripts to extract creation-time (T0) features from the AIDev dataset, train/evaluate the triage models (LightGBM and baselines), and reproduce the main tables/figures reported in the paper (performance, top-K utility, calibration, robustness checks). The package is anonymized for double-blind review; dataset access follows the AIDev preprint and official download instructions. See README inside the zip for step-by-step reproduction.
AIDev, Software engineering, Human-AI collaboration, Pull request triage, MSR2026, Review effort, Agentic pull requests, Ghosting, Mining Challenge
AIDev, Software engineering, Human-AI collaboration, Pull request triage, MSR2026, Review effort, Agentic pull requests, Ghosting, Mining Challenge
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!